Advertisement

Statistical Utterance Selection Using Word Co-occurrence for a Dialogue Agent

  • Naoki Isomura
  • Fujio Toriumi
  • Kenichiro Ishii
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5925)

Abstract

In this paper, we proposed a statistical utterance selection method for dialogue agents by applying a machine learning algorithm. We defined statistical candidate utterance selection as a question that automatically selects an appropriate utterance from speech collections prepared in advance as responses. To realize automatic utterance evaluation, we employed manually evaluated data as learning data so that relative magnitude correlation will be learned from them.

We checked the order of the automatically evaluated values to prove the validity of our proposed method. In this simulation, the result shows that the top appropriate utterance is selected at 47.5%, and it is selected within the top 10 at 78.0%. For implementing this method in agents that assist humans by replying, we found that it is quite possible to realize such an agent.

Keywords

machine learning utterance selection dialogue agent non-task-oriented dialogue 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Della Pietra, S., Della Pietra, V., Lafferty, J., Technol, R., Brook, S.: Inducing features of random fields. IEEE transactions on pattern analysis and machine intelligence 19(4), 380–393 (1997)CrossRefGoogle Scholar
  2. 2.
    Dunning, T.: Accurate methods for the statistics of surprise and coincidence. Computational linguistics 19(1), 61–74 (1993)Google Scholar
  3. 3.
    Haruno, M., Shirai, S., Ooyama, Y.: A japanese dependency parser based on a decision tree. Transactions of Information Processing Society of Japan 39(12), 3177–3186 (1998)Google Scholar
  4. 4.
    Inaba, M., Isomura, N., Toriumi, F., Ishii, K.: Evaluation method of Non-task-oriented dialogue system using Semantic Network. Technical report of IEICE (2009)Google Scholar
  5. 5.
    Isomura, N., Toriumi, F., Ishii, K.: Evaluation method of non-task-oriented dialogue system using HMM. The IEICE transactions on information and systems J92-D(4), 542–551 (2009)Google Scholar
  6. 6.
    Kudo, T., Kazawa, H.: Web japanese n-gram version 1, published by gengo shigen kyokaiGoogle Scholar
  7. 7.
    Kudo, T., Matsumoto, Y.: Japanese dependency parsing using relative preference of dependency. Transactions of Information Processing Society of Japan 46(4), 1082–1092 (2005)Google Scholar
  8. 8.
    Liu, D.C., Nocedal, J.: On the limited memory BFGS method for large scale optimization. Mathematical Programming 45(1), 503–528 (1989)zbMATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    Møller, M.: A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks 6, 525 (1993)CrossRefGoogle Scholar
  10. 10.
    Uchimoto, K., Sekine, S., Isahara, H.: Japanese dependency structure analysis based on maximum entropy models. Transactions of Information Processing Society of Japan 40(9), 3397–3407 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Naoki Isomura
    • 1
  • Fujio Toriumi
    • 1
  • Kenichiro Ishii
    • 1
  1. 1.Graduate School of Information ScienceNagoya UniversityJapan

Personalised recommendations